© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38996
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     up
    -1.44
     itſelf
    -1.28
     faſt
    -1.17
     myſelf
    -1.16
     themſelves
    -1.15
     himſelf
    -1.13
     pleaſure
    -1.12
     Efq
    -1.10
     Reſ
    -1.04
    ſelf
    -1.03
    POSITIVE LOGITS
    ,
    0.60
     from
    0.55
    ↵
    0.55
     (
    0.52
    .
    0.51
    ↵↵
    0.51
    <eos>
    0.50
     I
    0.50
    ;
    0.50
     The
    0.49
    Activations Density 0.086%

    No Known Activations